US 12,452,542 B2
Hallucinating details for over-exposed pixels in videos using learned reference frame selection
Iuri Frosio, Bergamo (IT); Yazhou Xing, Shenzhen (CN); Chao Liu, Pittsburgh, PA (US); Anjul Patney, Kirkland, WA (US); Hongxu Yin, San Jose, CA (US); Amrita Mazumdar, San Francisco, CA (US); and Jan Kautz, Lexington, MA (US)
Assigned to NVIDIA CORPORATION, Santa Clara, CA (US)
Filed by NVIDIA CORPORATION, Santa Clara, CA (US)
Filed on Jan. 5, 2024, as Appl. No. 18/406,006.
Claims priority of provisional application 63/481,380, filed on Jan. 24, 2023.
Prior Publication US 2024/0251171 A1, Jul. 25, 2024
Int. Cl. H04N 23/73 (2023.01); H04N 23/95 (2023.01)
CPC H04N 23/73 (2023.01) [H04N 23/95 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving one or more frames of a live video captured by a video capturing device, wherein the one or more frames include a current frame that is most-recently captured;
identifying a set of reference frames included in the one or more frames based on at least the current frame, wherein each frame in the set of reference frames has a different exposure level relative to the current frame;
determining, using one or more neural networks, a set of missing details for one or more regions of the current frame based on the set of reference frames;
generating an updated version of the current frame based on the set of details; and
outputting the updated version of the current frame in real-time for display.